SWARCH Model Research Articles

Attention Winged Deep Neural Early Warning System: How Does it Perform in Signaling Sovereign Crises for China?

This study efforts to construct an effective early warning system (EWS) to predict sovereign crises for China and distinguish different levels of leading determinants, such as macro-economic fundamentals and risk transmission factors, impact significance in signaling the volatility quantified crises. We contribute the literature for predicting the sovereign crisis in three aspects of first defining ‘Chinese-style’ sovereign crisis by referring to the national bond index high volatile state regardless of the subjectivity from rating agency judging and the verbosity from threshold selecting criteria for each determinants, first technically quantifying contagious factors given specific crisis origins by multiplying the SWARCH model estimated high volatility probabilities of contagious sources to the DCC-GARCH model estimated correlation coefficients and first implementing the statistical hypothesis test on stylized attention based neural networks to judge the inferred contributing degree’s credibility. We find the regime classification regime metric is essential to classify crises and in the predictive models horse-race, the attention mechanism based bidirectional LSTM networks outperforms others. For China, the gold price, constant price for real estate in GDP and technically quantified contagious index for between oil and CDB index are top three leading indicators drawn by the attention at appropriate significant levels.

Predicting currency crisis in Indonesia based on real output and Indonesia Composite Index (ICI) indicators

The currency crisis that occurred in the middle of 1997, 1998 and 4th quarter of 2008 was caused by disturbances in the currency system. When there is disturbance in the system then the cause indicators will experience fluctuations and changes in conditions. High fluctuation can be modeled using volatility model, while the changes in condition can be modeled using Markov switching model. Therefore, combination of volatility and Markov switching models is very appropriate to explain the crisis. In this paper, we use real output and ICI indicators on the period of January 1990 until December 2016 to explain the crisis as well as to forecast the possibility of an impending crisis. The results show that the appropriate model is ARCH (1) and Markov switching with 3 states, called SWARCH (3,1) model. This model can catch the crisis that happened in 1998 and 1999 for real output indicator. Meanwhile ICI indicator can explain the crisis in August to December 1997, 1998 and September to December 2008. Based on SWARCH (3,1) model, it can be predicted that Indonesia does not experience currency crisis in one year later.

Deteksi Krisis Keuangan di Indonesia Berdasarkan Indikator Nilai Tukar Riil Menggunakan Model SWARCH (2,3)

The financial crisis that hit Asia in mid-1997 began with the financial crisis in Thailand which then spread to Indonesia. The impact of the financial crisis in Indonesia is so severe that a crisis detection system is needed. The financial crisis detection system can be done by simple monitoring of macroeconomic indicators such as real exchange rate. Excessive real exchange rate is predicted to have a great chance of crisis.<br />The result shows that the real exchange rate from January 1990 to June 2013 has heteroscedasticity effect and there are structural changes so it can be modeled using SWARCH model (2,3) with ARMA (1.0) as conditional average model and ARCH (3) as model conditional variance. The inferred probabilities value of the SWARCH (2,3) model in February 1998 of 1 and July 1998 of 0.9968 over 0.5 indicates that the period is in a high volatile condition indicating a crisis. The SWARCH model (2.3) based on the real exchange rate indicator was able to capture the high volatile conditions in February 1998 and July 1998 as the impact of the 1997 Asian financial crisis.<br />Keywords : Deteksi, krisis keuangan, nilai tukar riil, SWARCH

Financial Crisis Forecasting in Indonesia Based on Bank deposits, Real Exchange Rates and Trade Terms Indicators

Indonesia has experienced a financial crisis several times, but the crisis that occurred in 1997 had a bad impact on the economy and national stability. Therefore, it needs a model that can be used to predict the condition ahead. This paper proposes forecasting the financial crisis in Indonesia. Bank deposits, real exchange rates and exchange rates of trade indicators are used in this paper. Data from January 1990 to December 2015 are used to form the models, while data from January to December 2016 are used to accurate the models. Combination of volatility and Markov switching models are used to model the data. The result suggests that the appropriate model for bank deposit and real exchange trade is SWARCH (3.1), and for real exchange rates is SWARCH (3.2). SWARCH (3.1) model has the accuracy 100%, while SWARCH (3.2) has the accuracy 75%. Based on these models, it can be forecasted that there is no financial crisis in Indonesia on 2017.

The models for financial crisis detection in Indonesia based on import, export, and foreign exchange reserves

The severity of the financial crisis that occurred in Indonesia required an early warning system of financial crisis. The financial crisis in Indonesia can be detected based on imports, exports, and foreign exchange reserves. The purpose of the research is to determine an appropriate model to detect the financial crisis in Indonesia based on imports, exports, and foreign exchange reserves. Markov switching is an alternative framework for the approach often used in financial crisis detection. Combined volatility and Markov switching model with three states assumptions can be established if an AR and volatility models have been obtained. Imports, exports, and foreign exchange reserves data from January 1990 to December 2016 have the heteroscedasticity effect so that an ARCH model is used as a volatility model. Research shows that SWARCH(3.1) model is an appropriate model for detecting financial crisis in Indonesia based on imports, exports, and foreign exchange reserves.

Markov Switching Autoregressive Conditional Heteroscedasticity (SWARCH) Model to Detect Financial Crisis in Indonesia Based on Import and Export Indicators

A country is said to be a crisis when the financial system is experiencing a disruption that affects systems that can not function efficiently. The performance efficiency of macroeconomic indicators especially in imports and exports can be used to detect the financial crisis in Indonesia. Based on the import and export indicators from 1987 to 2015, the movement of these indicators can be modelled using SWARCH three states. The results showed that SWARCH (3,1) model was able to detect the crisis that occurred in Indonesia in 1997 and 2008. Using this model, it can be concluded that Indonesia is prone to financial crisis in 2016.

Estimation of Volatility in International Business Cycles in Korea and Selected Developed Countries under the Financial Crises

This study examined the structural changes in volatility in the international business cycles using the real GDP during financial crises within the 1971-2016 period. The coefficients did not appear to reflect unstable structural changes during a financial crisis as seen in Chow tests. On the other hand, the 1-Step tests showed stable and/or unstable coefficients except in Canada and Korea, but these were persistently stable in the N-Step tests except for Germany and Japan where such coefficients were unstable. In the CUSUM tests, the coefficients were stable over the periods. The CUSUMSQ tests showed stable coefficients in the country except Korea and UK. Korea exhibited higher regime switching volatility probability which suggests that significant changes in SWARCH model may have to be made. Transition probability showed the highest duration in the low regime in Canada. The MS-VAR models demonstrated significant simultaneous structural changes in volatility in international economic cycles as a result of the market crash. Korea was significantly affected and transmitted by the real GDP of the countries through the Asia and Global financial crisis. Therefore, we found structural changes in volatility in the international business cycles as a result of simultaneous symmetric or asymmetric shocks between Korea and major developed countries and we confirmed that the high volatility (contraction) regime coincided with the financial crises.

Switching volatility and cross-market linkages in public property markets

The primary contribution of this study is to examine the changes in cross-market relationship in international public property markets from a volatility regime switching perspective from January 1990 to January 2012. We find that global developed public property markets can be adequately characterised by a SWARCH model. In particular, most of the persistence in real estate stock price volatility can be attributed to the persistence of low-, medium- and high-volatility regimes in international developed public property markets. Moreover, there is a significant volatility increase during the crises periods for all markets examined. However, the identified high-volatility regime appears short-lived. Based on the SWARCH results, we find that the dynamic linkages among the markets are positively dependent on volatility regime. Specifically, the market correlations, foreign market influence, aggregate variance spillover index and variance–covariance matrix have intensified as market volatility increases during this period. Moreover, the evolution of the cross-market linkages among the sample public property markets is influenced significantly by both a time trend and a volatility regime factor that are independent of the influences of the global stock market and national stock markets. Our results imply that risk-reduction via international diversification in public property markets may only hold true in low-volatility periods. Consequently, portfolio managers need to understand and implement volatility state-dependent optimal asset allocation in order to better advise their clients.

Variance-Based Spillover Analysis between Stock Markets: A Time Varying Parameter Approach

This paper proposes a variance-based spillover impact analysis embedded with a dynamic Kalman ltering in order to detect a causality relationship from the US stock markets into the European and emerging stock markets during the nancial crisis. It has mainly two new contributions to the literature. Firstly, it uses variance rather than returns to analyze the spillover impact between the markets. Secondly, and more importantly, it is an econophysics research as it examines causality relationship with the Kalman ltering in physics. We calculate time-dependent conditional stock market variances for Dow Jones, DAX, FTSE, RTS (Russia), and BIST (Turkey) by employing SWARCH model. The empirical analysis examines the causal relationship between Dow Jones into the other stock markets employing Granger causality tests in order to detect the direction of volatility spillover relationship. As an embedded analysis, we follow a dynamic approach by using the Kalman ltering as a time varying parameter model to depict the time varying interaction between stock markets volatilities. The empirical results point out unidirectional Granger causality from Dow Jones to the other markets indicating the spillover impact of the volatility starting from the US markets and expanded into the world in the latest global crisis.

Examining Stock Volatility in the Segmented Chinese Stock Markets: A SWARCH Approach

This study adopts the SWARCH model to examine the volatile behavior and volatility linkages among the four major segmented Chinese stock indices. We find strong evidence of a regime shift in the volatility of the four markets, and the SWARCH model appears to outperform standard generalized autoregressive conditional heteroskedasticity (GARCH) family models. The evidence suggests that, compared with the A-share markets, B-share markets stay in a high-volatility state longer and are more volatile and shift more frequently between high- and low-volatility states. In addition, the relative magnitude of the high-volatility compared with that of the low-volatility state in the B-share markets is much greater than the case in the two A-share markets. B-share markets are found to be more sensitive to international shocks, while A-share markets seem immune to international spillovers of volatility. Finally, analyses of the volatility spillover effect among the four stock markets indicate that the A-share markets play a dominant role in volatility in Chinese stock markets.

Modelling house price volatility states in the UK by switching ARCH models

This article analyses investment risk in the housing market by examining volatility properties of house prices for the UK. We use both ARCH and GARCH models to estimate price conditional heteroscedasticity and find evidence of a time-varying property in the volatilities of the house price series. We then use the SWARCH model and find there are three volatility states in the price series. Our estimations suggest the UK housing markets are relatively stable and different states do not switch very often. The magnitude of high price volatility is as high as 20.99 times of the low volatility for the older housing market and 14 times of the low volatility for the new housing market. In addition, the older housing market is less efficient than the new housing market, since the impacts of events on the volatility state of the older house prices is more lasting than in new housing market.

Stock Volatility in the Segmented Chinese Stock Markets: A SWARCH Approach

This study adopts the Markov-switching ARCH (hereafter SWARCH) model to examine the volatility nature and volatility linkages of four segmented Chinese stock indices (SHA, SZA, SHB, and SZB). Our empirical findings are consistent with the following notions. First, we find strong evidence of regime shift in the volatility of four segmented markets and SWARCH model appears to outperform standard GARCH family models. Second, although there are some common features of volatility switch in segmented markets, there exist a few difference: (i)compared with the A-share markets, B-share markets are more volatile and shift more frequently between high- and low-volatility states; (ii) B-share markets have longer stays at high volatility state than the A-share markets; (iii) the relative magnitude of the high volatility compared with that of the low volatility is much greater than the case in two A-share markets. Third, B-share markets are found to be more sensitive to international shocks, while the A-share markets seem immune to international spillovers of volatility. Finally, analyses of volatility spillover effect among the four stock markets indicate that the A-share markets play a dominant role in volatility in Chinese stock markets.

REGIME-SWITCHED VOLATILITY OF BRENT CRUDE OIL FUTURES WITH MARKOV-SWITCHING ARCH MODEL

This paper investigates the volatility process of the Brent crude oil futures markets using Markov-switching ARCH (SWARCH) model. The SWARCH model allows the conditional disturbances to change as time passes and even to switch in different regimes. The empirical evidence shows that the SWARCH (3,3) model performs the best goodness of fit and the best forecast performance among different fitting models. The estimation of smoothing probabilities of data under different regimes facilitates to capture the characteristics of the data, and the high-volatility regime is associated with some extraordinary events, such as the 1990's Persian Gulf War, the 1997's Asia Financial Crisis, and the 2001's 911 terrorist attack.

Examining the Volatility of Taiwan Stock Index Returns via a Three-Volatility-Regime Markov-Switching ARCH Model

This study adopts Hamilton and Susmel's (1994) Markov-switching ARCH (hereafter SWARCH) model to examine the volatility of the valued-weighted Taiwan Stock Index (hereafter TAIEX) returns. We also conduct sensitivity tests on comparison observations of Dow Jones and Nikkei stock indices. Our empirical findings are consistent with the following notions. First, the SWARCH model appears to outperform the competing ARCH and GARCH models in estimating the volatilities of TAIEX. Second, the three-volatility-regime setting is descriptive for TAIEX and Nikkei. In contrast with Hamilton and Susmel (1994), the contemporaneous Dow Jones adopted in this paper has only two regimes. Our test results suggest that the optimal number of volatility regimes is sensitive to the choice of sample periods. Third, our empirical results also lend an explanation to such phenomenon: the probability that TAIEX directly moves from a low (high) volatility regime to the high (low) volatility regime approaches zero, whereas TAEIX happened to be in a low volatility regime during the pre-financial-crisis period from April, 1996 to July, 1997. These can explain why Taiwan was one of Asia's few star performers compared with recession-hit neighbors during the first eighteen months of Asia's financial crisis.

Is the covariance of international stock market returns regime dependent?

The application of a SWARCH model to stock market returns allows one to endogenously determine the regime dependence of the stock market volatility. Comparison of the results from a sample of daily data from five major stock markets shows that the majority of the markets switch regimes simultaneously. This fact is used to investigate the relation between market volatility and the behaviour of the variance—;covariance matrix. It is found that the international variance—;covariance matrix is not stable and that changes in the matrix are dependent on the volatility regime. A high level of variance causes an increase in the average correlation coefficient. The co-movement of the markets is further described by a steady increase in the covariance over the whole sample period. It can be shown that both the time component and the regime dependence of the average correlation have separate and significant explanatory power.

Is the covariance of international stock market returns regime dependent?

The application of a SWARCH model to stock market returns allows one to endogenously determine the regime dependence of the stock market volatility. Comparison of the results from a sample of daily data from five major stock markets shows that the majority of the markets switch regimes simultaneously. This fact is used to investigate the relation between market volatility and the behaviour of the variance—;covariance matrix. It is found that the international variance—;covariance matrix is not stable and that changes in the matrix are dependent on the volatility regime. A high level of variance causes an increase in the average correlation coefficient. The co-movement of the markets is further described by a steady increase in the covariance over the whole sample period. It can be shown that both the time component and the regime dependence of the average correlation have separate and significant explanatory power.

The credibility of the Colombian exchange rate target zone: Its impact over the volatility of interest rate differentials

This paper analyzes the credibility of Colombia’s exchange rate target zone, and in particular its impact on the volatility of interest rate differentials. Bertola and Caballeros’ (1995) model of a target zone with imperfect credibility is used to derive the impact of a reduction in credibility over the variance of the interest rate differential. It is theoretically shown, that as credibility decreases the variance of the interest rate differential increases. This theoretical argument is used to estimate credibility in Colombia’s exchange rate target zone. Using a SWARCH model, the probability of being in a regime with high interest rate volatility is estimated, and is related with events in the exchange rate market. Results suggest that there is evidence of lack of credibility even before the recent international financial turmoil was triggered.

Estimating and Forecasting the Volatility of Brazilian Finance Series Using ARCH Models

The goal of this paper is to present a comprehensive emprical analysis of the return and conditional variance of four Brazilian financial series using models of the ARCH class. Selected models are then compared regarding forecasting accuracy and goodness-of-fit statistics. To help understanding the empirical results, a self-contained theoretical discussion of ARCH models is also presented in such a way that it is useful for the applied researcher. Empirical results show that although all series share ARCH and are leptokurtic relative to the Normal, the return on the US$ has clearly regime switchlng and no asymmetry for the variance, the return on COCOA has no asymmetry, while the returns on the Cbond and Telebras have clear signs of asymmetry favoring the leverage effect. Regarding forecasting, the best model overall was the EGARCH(l,l) in its Gaussian version. Regarding goodness-of-fit statistics, the SWARCH model did well, followed closely by the Student-t GARCH(l,l).

Does the Introduction of Futures on Emerging Market Currencies Destabilize the Underlying Currencies?

Recent interest in futures contracts on emerging market currencies has raised concerns among some central bank authorities about their ability to maintain stable currencies. This paper presents empirical results examining the influence of the Mexican peso, the Brazilian real, and the Hungarian forint futures contracts on the respective spot markets. While measures of linear dependence and feedback indicate strong connections between the respective markets, futures volatility does not significantly explain spot market volatility, nor does it increase after futures introductions. To account for the characteristics of the spot and futures returns, a SWARCH model is employed to estimate volatility.

The dynamics of DM/£ exchange rate volatility: a SWARCH analysis

This paper applies the switching ARCH model introduced by Hamilton and Susmel (1994) to weekly DM/£ exchange rates for the period March 1987–December 1994. The sample period spans the UK's ERM tenure, which lasted until the currency crisis of September 1992. The SWARCH model generalizes standard ARCH models by allowing the conditional variance to experience jumps between discrete states or regimes. The SWARCH model is shown to provide a unified statistical framework for investigating two issues of interest in the literature: (i) the evolution of volatility and its implications for ERM credibility and (ii) the effects of regime shifts on the stochastic process governing conditional volatility. © 1998 John Wiley & Sons, Ltd.